train.py

import tensorflow as tf
from keras.preprocessing.image import ImageDataGenerator
train_datagen = ImageDataGenerator(rescale = 1./255,
                                   shear_range = 0.2,
                                   zoom_range = 0.2,
                                   horizontal_flip = True)
training_set = train_datagen.flow_from_directory('tomato/train',
                                                 target_size = (128, 128),
                                                 batch_size = 64,
                                                 class_mode = 'categorical')

test_datagen = ImageDataGenerator(rescale = 1./255)
test_set = test_datagen.flow_from_directory('tomato/val',
                                            target_size = (128, 128),
                                            batch_size = 64,
                                            class_mode = 'categorical')

cnn = tf.keras.models.Sequential()
cnn.add(tf.keras.layers.Conv2D(filters=32, kernel_size=3, activation='relu', input_shape=[128, 128, 3]))
cnn.add(tf.keras.layers.MaxPool2D(pool_size=2, strides=2))
cnn.add(tf.keras.layers.Conv2D(filters=32, kernel_size=3, activation='relu'))
cnn.add(tf.keras.layers.MaxPool2D(pool_size=2, strides=2))
cnn.add(tf.keras.layers.Flatten())
cnn.add(tf.keras.layers.Dense(units=128, activation='relu'))
cnn.add(tf.keras.layers.Dense(units=10, activation='sigmoid'))
cnn.compile(optimizer = 'adam', loss = 'categorical_crossentropy', metrics = ['accuracy'])
cnn.fit(x = training_set, validation_data = test_set, epochs = 50,steps_per_epoch = 20)

classifier_json=cnn.to_json()
with open("model1.json", "w") as json_file:
    json_file.write(classifier_json)
# serialize weights to HDF5
    cnn.save_weights("my_model_weights.h5")
    cnn.save("model.h5")
    print("Saved model to disk")